The image texture features obtained from ¹⁸F-fluorodeoxyglucose positron emission tomography/computed tomography (¹⁸F-FDG PET/CT) images of non-small cell lung cancer (NSCLC) have revealed tumor heterogeneity. A combination of genomic data and radiomics may improve the prediction of tumor prognosis. This study aimed to predict NSCLC metastasis using a graph neural network (GNN) obtained by combining a protein–protein interaction (PPI) network based on gene expression data and image texture features. ¹⁸F-FDG PET/CT images and RNA sequencing data of 93 patients with NSCLC were acquired from The Cancer Imaging Archive. Image texture features were extracted from ¹⁸F-FDG PET/CT images and area under the curve receiver operating characteristic curve (AUC) of each image feature was calculated. Weighted gene co-expression network analysis (WGCNA) was used to construct gene modules, followed by functional enrichment analysis and identification of differentially expressed genes. The PPI of each gene module and genes belonging to metastasis-related processes were converted via a graph attention network. Images and genomic features were concatenated. The GNN model using PPI modules from WGCNA and metastasis-related functions combined with image texture features was evaluated quantitatively. Fifty-five image texture features were extracted from ¹⁸F-FDG PET/CT, and radiomic features were selected based on AUC (n = 10). Eighty-six gene modules were clustered by WGCNA. Genes (n = 19) enriched in the metastasis-related pathways were filtered using DEG analysis. The accuracy of the PPI network, derived from WGCNA modules and metastasis-related genes, improved from 0.4795 to 0.5830 (p < 2.75 × 10⁻¹²). Integrating PPI of four metastasis-related genes with ¹⁸F-FDG PET/CT image features in a GNN model elevated its accuracy over a without image feature model to 0.8545 (95% CI = 0.8401–0.8689, p-value < 0.02). This model demonstrated significant enhancement compared to the model using PPI and ¹⁸F-FDG PET/CT derived from WGCNA (p-value < 0.02), underscoring the critical role of metastasis-related genes in prediction model. The enhanced predictive capability of the lymph node metastasis prediction GNN model for NSCLC, achieved through the integration of comprehensive image features with genomic data, demonstrates promise for clinical implementation.

Chemotherapy response and metastasis prediction play important roles in the treatment of pediatric osteosarcoma, which is prone to metastasis and has a high mortality rate. This study aimed to estimate the prediction model using gene expression and image texture features. 18F-fluorodeoxyglucose positron emission tomography/computed tomography (¹⁸F-FDG PET/CT) images of 52 pediatric osteosarcoma patients were used to estimate the machine learning algorithm. An appropriate algorithm was selected by estimating the machine learning accuracy. ¹⁸F-FDG PET/CT images of 21 patients were selected for prediction model development based on simultaneous KI67 and EZRIN expression. The prediction model for chemotherapy response and metastasis was estimated using area under the curve (AUC) maximum image texture features (AUC_max) and gene expression. The machine learning algorithm with the highest test accuracy in chemotherapy response and metastasis was selected using the random forest algorithm. The chemotherapy response and metastasis test accuracy with image texture features was 0.83 and 0.76, respectively. The highest test accuracy and AUC of chemotherapy response with AUC_max, KI67, and EZRIN were estimated to be 0.85 and 0.89, respectively. The highest test accuracy and AUC of metastasis with AUC_max, KI67, and EZRIN were estimated to be 0.85 and 0.8, respectively. The metastasis prediction accuracy increased by 10% using radiogenomics data.

Dicentric chromosome assay (DCA) is one of the cytogenetic dosimetry methods where the absorbed dose is estimated by counting the number of dicentric chromosomes, which is a major radiation-induced change in DNA. However, DCA is a time-consuming task and requires technical expertise. In this study, a neural network was applied for automating the DCA. We used YOLOv5, a one-stage detection algorithm, to mitigate these limitations by automating the estimation of the number of dicentric chromosomes in chromosome metaphase images. YOLOv5 was pretrained on common object datasets. For training, 887 augmented chromosome images were used. We evaluated the model using validation and test datasets with 380 and 300 images, respectively. With pretrained parameters, the trained model detected chromosomes in the images with a maximum F1 score of 0.94 and a mean average precision (mAP) of 0.961. Conversely, when the model was randomly initialized, the training performance decreased, with a maximum F1 score and mAP of 0.82 and 0.873%, respectively. These results confirm that the model could effectively detect dicentric chromosomes in an image. Consequently, automatic DCA is expected to be conducted based on deep learning for object detection, requiring a relatively small amount of chromosome data for training using the pretrained network.

The acquisition of in vivo radiopharmaceutical distribution through imaging is time-consuming due to dosimetry, which requires the subject to be scanned at several time points post-injection. This study aimed to generate delayed positron emission tomography images from early images using a deep-learning-based image generation model to mitigate the time cost and inconvenience. Eighteen healthy participants were recruited and injected with [¹⁸F]Fluorodeoxyglucose. A paired image-to-image translation model, based on a generative adversarial network (GAN), was used as the generation model. The standardized uptake value (SUV) mean of the generated image of each organ was compared with that of the ground-truth. The least square GAN and perceptual loss combinations displayed the best performance. As the uptake time of the early image became closer to that of the ground-truth image, the translation performance improved. The SUV mean values of the nominated organs were estimated reasonably accurately for the muscle, heart, liver, and spleen. The results demonstrate that the image-to-image translation deep learning model is applicable for the generation of a functional image from another functional image acquired from normal subjects, including predictions of organ-wise activity for specific normal organs.

The purpose of this study was to investigate the most appropriate methodological approach for the automatic measurement of rodent myocardial infarct polar map using histogram-based thresholding and unsupervised deep learning (DL)-based segmentation. A rat myocardial infarction model was induced by ligation of the left coronary artery. Positron emission tomography (PET) was performed 60 min after the administration of ¹⁸F-fluoro-deoxy-glucose (¹⁸F-FDG), and PET was performed after injecting ⁶⁴Cu-pyruvaldehyde-bis(N4-methylthiosemicarbazone). Single photon emission computed tomography was performed 60 min after injection of ^99mTc-hexakis-2-methoxyisobutylisonitrile and ²⁰¹Tl. Delayed contrast-enhanced magnetic resonance imaging was performed after injecting Gd-DTPA-BMA. Three types of thresholding methods (naive thresholding, Otsu’s algorithm, and multi-Gaussian mixture model (MGMM)) were used. DL segmentation methods were based on a convolution neural network and trained with constraints on feature similarity and spatial continuity of the response map extracted from images by the network. The relative infarct sizes measured by histology and estimated R² for ¹⁸F-FDG were 0.8477, 0.7084, 0.8353, and 0.9024 for naïve thresholding, Otsu’s algorithm, MGMM, and DL segmentation, respectively. DL-based method improved the accuracy of MI size assessment.